Downloads · 30 days
157
12% of all-time downloads
Qwen3.8-27B-MLX-mixed-6bit
TheCluster/Qwen3.8-27B-MLX-mixed-6bit
Qwen3.8-27B-MLX-mixed-6bit is a image-text-to-text model from TheCluster. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. It is set up for mlx. The card lists the license as apache-2.0.
Quality: quantized (mixed quants per tensor, group size: 32, 6.096 bpw)
All-time downloads
1.3K
Public
Parameters
27.4B
20.9 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors20.8 GB · 100%
Parameter types
How the weights are stored.
U3226.9B · 98%
Try a prompt
Base models
Model card
From the Hugging Face model README
Qwen3.8-27B
Quality: quantized (mixed quants per tensor, group size: 32, 6.096 bpw)
Most tensors use 4-bit, 6-bit or 8-bit affine quantization with a group size 32.
Update: default reasoning_effort is set to 'low' to avoid overthinking.
Recommended settings
-
Sampling Parameters: The developers suggest using the following sets of sampling parameters:
- Thinking Mode:
temperature=1.0,top_p=0.95,top_k=20,min_p=0.0,presence_penalty=0.0,repetition_penalty=1.0 - Instruct (or non-thinking) mode:
temperature=0.7,top_p=0.80,top_k=20,min_p=0.0,presence_penalty=1.5,repetition_penalty=1.0
For supported frameworks, you can adjust the
presence_penaltyparameter between 0 and 2 to reduce endless repetition. However, using a higher value may occasionally result in language mixing and a slight decrease in model performance. - Thinking Mode:
Source
This model was converted to MLX format from Qwen/Qwen3.8-27B using mlx-vlm version 0.6.13.
- Task
- Image-Text-to-Text
- Library
- mlx
- Type
- qwen3_5
- License
- apache-2.0
- Languages
- en, zh, ru, es, fr, it
- Created
- Aug 14, 2026
- Updated
- Aug 19, 2026